Loading video...

Video Failed to Load

Go Home

THIS GUY CONNECTED CLAUDE VOICE MODE TO CLAUDE CODE AND NOW HE CODES BY TALKING INTO HIS AIRPODS while doing whatever he wants he uses Apple Reminders as a bridge between the two he talks into his AirPods, voice mode puts the prompt into a reminders list, Claude Code...

151,333 views • 6 months ago •via X (Twitter)

33 Comments

The Swiss Hedgehog's profile picture
The Swiss Hedgehog6 months ago

Awesome! You can do that as well with . Log ideas or have an interactive planning session for new features while walking or at the gym, then tell agents to implement. Come back to the desk for PRs reviews. I actually fixed bugs in prod with my phone while skiing the other day! 🤣

Michal Takac's profile picture
Michal Takac6 months ago

I’m working on similar experience for but for XR and AI glasses, so you work around and build the environment / experience you want being in it. Plus a new thing I call “GEVL” for now - grasp > evaluate > visualize > loop

Brian Johnson's profile picture
Brian Johnson6 months ago

walking + thinking + code writing itself at home is genuinely the unlock nobody talks about. best ideas don't happen at a desk

Michael Billett's profile picture
Michael Billett6 months ago

I need the dets. Or I’ll just vibe code the bridge myself… either way, walking brainstorms are my unlock as well!

Jacob Shi's profile picture
Jacob Shi6 months ago

apple reminders as a coding task queue is so cursed and so genius at the same time. siri never asked for this responsibility

Brian Harms's profile picture
Brian Harms6 months ago

For those wondering, since this is my work: if this doesn’t appeal to you, you probably don’t use Claude code the way I do. Today I walked to my office with a new idea in mind. I started Claude voice mode and put my phone in my pocket. We went back and forth for 45 min discussing an idea: the architecture, the ux, the technical details. It goes “great, are you ready to send that to Claude code?” Nope, I want to keep brainstorming. Ok great, now I’m ready, go ahead and send it. I get to my desk and Claude code has something for me to review. Didn’t look at my phone once (except to start the convo). If you like having more friction than that, then I can’t argue with you.

OneManSaas's profile picture
OneManSaas6 months ago

Clever workaround but Apple Reminders as middleware feels fragile. I'd probably use Zapier or a simple webhook to connect them directly - one less point of failure when you're trying to stay in flow.

Chan's profile picture
Chan6 months ago

Peak civilization is debugging by mumbling while walking to get coffee.

Alfredo Canziani's profile picture
Alfredo Canziani6 months ago

Where is the link to the repo???

LoopCast's profile picture
LoopCast6 months ago

this is the future of productivity. when ai can handle the routine, creators are free to focus on the truly innovative.

Shaun's profile picture
Shaun6 months ago

Why not just use telegram to message to agent system? Then it’s in a conversation and you can explore the thread. Honest qn because I’m still not yet started but will be setting up Hermes’ this week

MetaMike's profile picture
MetaMike6 months ago

Ooenvoicui you can build games apps whatever you want with your voice

🟢 Dakari¥Doggz | AeUISHx's profile picture
🟢 Dakari¥Doggz | AeUISHx6 months ago

he walks outside and codes, already not knowing anything about what he's coding, gives coding instructions and extra doesnt, cannot check it, then what? sorry i got lost somewhere in the stupidness being presented as bright.

Wesley Huber's profile picture
Wesley Huber6 months ago

/ultraplan feels like having a senior eng quietly gut check everything... being able to add inline comments before pushing the plan back to the CLI just saved me from blowing away an entire repo

Ramy Wafaa's profile picture
Ramy Wafaa6 months ago

walk outside. think out loud. come back to working code. that's genuinely a different relationship with building. the barrier between having an idea and acting on it just collapsed 🤯

Mr. Herb's profile picture
Mr. Herb6 months ago

Can you tag the guy ?

Tom's profile picture
Tom6 months ago

most people overthink the setup when the real edge is just reducing friction between idea and execution

@joelcressy.dev's profile picture
@joelcressy.dev6 months ago

how does he get responses back? like to approve tool calls or watch the agent's progress and send steering prompts?

nicholas ⛱'s profile picture
nicholas ⛱6 months ago

i do not believe the voice mode in claude app did anything useful

Chad King's profile picture
Chad King6 months ago

why did anthropic not build this? always baffles me

brian's profile picture
brian6 months ago

This is @therituallab and this is like 1% of his stuff. Dude is cracked.

Shaun Patrick SteWaRt's profile picture
Shaun Patrick SteWaRt6 months ago

I just connected Gemma 4 to Claude CLI to xAI and managed by Claude Code. All fully autonomous in all work now too. 🍆 claude-respond

steve's profile picture
steve6 months ago

Data shortcuts coded ass solution

Freezerburn's profile picture
Freezerburn6 months ago

I built on his idea and have control from my Apple Watch as well.

andrea's profile picture
andrea6 months ago

i built an ios app -> openclaw. does anyone want that

Endrew Cruz's profile picture
Endrew Cruz6 months ago

you can build once and let it run while you live life on your own terms

Ethan's profile picture
Ethan6 months ago

This is really cool. Almost feels like the movie Her

The Hounder's profile picture
The Hounder6 months ago

Fascinating

Xiao Dou's profile picture
Xiao Dou6 months ago

This is a great tool, but the actual operation is still quite complex. Typically, my workflow involves making sure I can see exactly what I’ve said before letting the AI execute it. Voice recognition patterns aren't always 100% accurate, so it still requires a manual check.

Coinkong's profile picture
Coinkong6 months ago

This is really cool. Almost feels like the movie Her

Me Mate, Argyle's profile picture
Me Mate, Argyle6 months ago

Link openclaw to telegram and spit voice commands back and forth to actively develop while mobile.

Chat Data's profile picture
Chat Data6 months ago

The reminders bridge is clever because it turns voice into a queue instead of a one shot command. That usually makes these workflows much more usable in real life. The next unlock is adding review and traceability so you can see which spoken prompt created which code change.

Jerry • HZN | 🌩's profile picture
Jerry • HZN | 🌩6 months ago

Can't wait for this to be normal , for now, what will i do if im outside and i reach my session limit !?

Related Videos

Noah Brier (Noah Brier) uses Claude Code as his second brain—it’s the coolest notetaking setup I’ve ever seen. He has Claude running on a server in his basement hooked up to a VPN. It stores, reads, and writes to thousands of notes in his Obsidian (Obsidian) vault. He does it all from his phone. I had him on the show to tell us exactly how he’s pulling this off. We get into: - The nuts and bolts of the Claude Code-Obsidian setup: Noah set up Claude Code on top of his Obsidian root directory, and he walked me through how he uses it to prep for an upcoming speech—creating a project folder, pulling in relevant research from his notes, saving transcripts from chats with other LLMs, and generating daily progress updates. - The “thinking partner” that lives inside Noah’s second brain: Noah points out that in the hype around AI’s ability to write, the fact that it can read is overlooked. That’s why he has an agent inside Claude Code with strict guardrails to stay in “thinking mode.” It logs his questions, tracks insights, and catches him up on research if he returns to a project after a few days away. - How Noah does deep work on his phone: Noah rigged a home server in his basement, put his Obsidian vault in it—and then runs Claude Code on top. Noah says that being able to think, write, research, and ship code from his phone has fundamentally changed the way he works. This episode of Every 📧’s AI & I is a must-watch for anyone curious about who wants to learn how to use Claude Code to build a true second brain. Watch below! Timestamps: Introduction: 00:01:19 How you can do deep work on your phone: 00:04:28 Why Noah thinks Grok has the best voice AI: 00:06:14 The nuts and bolts of Noah’s Claude Code-Obsidian setup: 00:11:39 Using an agent in Claude Code as a “thinking partner”: 00:23:59 Noah’s Thomas’ English Muffin theory of AI: 00:35:07 The white space still left to explore in AI: 00:44:04 How Noah is preparing his kids for AI: 00:50:41 How he brought his Claude Code setup to mobile: 01:01:54

Dan Shipper 📧

30,792 views • 1 year ago

An 18 year old told his dad he needed an Apple Vision Pro for university. Dad said that's a $3,500 movie headset, you don't need it for school. He said it runs macOS apps natively. Dad didn't know what that means. Bought it for graduation. $3,500. He never watched a single movie on it. Installed VS Code and Claude Code the same night. Threw six floating screens around his bedroom. Lay down in bed and started coding from under the sheets with his bare hands tapping air. His roommate walked in at 2am and saw him lying in bed wearing a headset waving his hands at nothing. Thought he was losing his mind. He was building a client website. At second 0:11 you can see his hand swipe across a floating file explorer. Behind it five more windows are open. All running Claude Code agents on different projects. One building, one testing, one deploying, one reviewing, one handling client messages. All floating above his bed like a command center in a sci-fi movie. The website color change was the demo he filmed. The five windows behind it were the actual business. Within a month he was running projects for seven clients. A restaurant site, an appointment app for a dentist, a landing page for a real estate agent, a dashboard for a gym owner. All built from bed. All coded by Claude while he gave instructions by tapping floating windows above his pillow. $11,400 in his first month. His dad makes $9,200 at his engineering job. His dad called last weekend and asked if the headset was worth it. He said yeah the movies are great. His dad said good, at least you're relaxing after studying. He wasn't studying. He wasn't watching movies. He was lying in bed while five Claude Code agents built software in floating windows above his face. A developer in New York rents a $2,800 apartment just to have a home office with two monitors. This kid has six floating screens that follow him from bed to couch to kitchen and cost nothing after the headset. His mom asked to try the Vision Pro last Sunday. Put it on and saw six VS Code windows floating in the living room, git commits scrolling, Claude mid-task on three projects. She took it off and said I thought this was for watching movies. He said it is. Just not the kind she was thinking of. Setup time: one evening. Screens: six, floating, invisible to everyone else in the room. Money made in month one: $11,400. Movies watched: zero. His dad is still paying off the $3,500. The headset paid for itself in 9 days. Dad doesn't know that yet. He will when his son offers to pay him back.

Marlow

714,689 views • 6 months ago

ONE OF ANTHROPIC'S CODERS SHARED HIS "SECOND BRAIN" HE'S BEEN BUILDING FOR 3 MONTHS. I WASN'T READY FOR WHAT I SAW he didn't post this on twitter. didn't make a thread. didn't record a youtube video. just showed me on a call and said "look what i've got" when i opened it - 2000+ notes. all connected to each other. looked like a map of the universe and at the center of it all - one file. CLAUDE.md it's not a prompt. it's a full profile of a person. who he is. how he thinks. what he's working on. where he gets stuck. how he wants the AI to talk to him. even his weaknesses claude reads this file first. every time. automatically. never starts a conversation from zero i asked him "so what did this change?" he said: "i stopped spending time explaining. now i spend time thinking" but that's just the beginning. every project has its own folder. clean structure. when he works on something - claude only sees that project. not the entire chaos anything he does more than once is saved as a skill. one line and claude does it his way and at 7am every day claude walks through the entire vault on its own. finds new stuff. links it. cleans what's stale. writes him 3 lines: what changed overnight he wakes up and the brain already worked and here's what got me the most: it's all just text files. no cloud. no subscription. no dependency on one service. if a better model drops tomorrow he just points it at the same folder he basically uploaded himself into a file system. and now AI doesn't guess who he is. AI knows most people use claude like google with manners. this guy built himself an external memory that grows every day full breakdown in the video tomorrow i'll show how i set this up myself in one evening. if you don't follow - you won't see it

kai

47,527 views • 3 months ago